PDF Data Extraction Toolkit

Turn unstructured PDFs into clean, structured data. This 16KB skill covers 5 extraction strategies: native text extraction (pymupdf), layout-aware parsing (pdfplumber), OCR for scanned documents (tesseract), table extraction to CSV/JSON, and form field extraction from fillable PDFs. Includes ready-to-use patterns for invoice parsing (line items, totals, dates, PO numbers), contract analysis (key terms, dollar amounts, durations, governing law), receipt OCR, and PDF-to-Markdown conversion. Handles edge cases: encrypted PDFs, mixed text+scanned pages, memory-efficient streaming for large files, batch directory processing. Every pattern outputs clean JSON, CSV, or Markdown. CLI one-liners included for quick extraction, image extraction, word frequency analysis, and PDF diffing. If your agent touches PDFs — invoices, reports, contracts, forms — this skill pays for itself on the first use.